Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65064
    Prev
    Next
    INDEX
    Explanations

    seeds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     meng
    -0.09
    MAIN
    -0.09
    actal
    -0.08
     meny
    -0.08
    onz
    -0.08
    DOS
    -0.08
    SCRIBE
    -0.08
    treme
    -0.08
    COUR
    -0.07
    ACT
    -0.07
    POSITIVE LOGITS
    ,例如
    0.10
    ,比如
    0.08
     flax
    0.08
    ,如
    0.08
     પાસ
    0.08
     Hana
    0.07
    .wallet
    0.07
    类
    0.07
    ਾਵ
    0.07
    ,与
    0.07
    Activations Density 0.002%

    No Known Activations